© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 1217
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mathews"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals named Matthews or variants of that name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Europa
    -0.79
     Euro
    -0.77
     Il
    -0.70
     Tour
    -0.68
     Culture
    -0.68
     lib
    -0.66
     vir
    -0.64
     culture
    -0.64
     incub
    -0.63
     export
    -0.63
    POSITIVE LOGITS
    hews
    4.07
    hew
    3.45
    anz
    1.33
    anut
    1.29
    icut
    1.17
    hes
    1.12
    terson
    1.09
    arnaev
    1.09
    hend
    1.06
    helle
    1.06
    Activations Density 0.024%

    No Known Activations